Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 103037
    Prev
    Next
    INDEX
    Explanations

    full-width Chinese characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     અભ
    -0.08
    ಿಕೆಯ
    -0.08
     વેચ
    -0.08
     Venda
    -0.08
    કે
    -0.08
     શ્ર
    -0.08
     Baut
    -0.08
    ಿಲ
    -0.07
     ક્ર
    -0.07
     સ્થાન
    -0.07
    POSITIVE LOGITS
     ağır
    0.09
    Unsupported
    0.08
    CONTENT
    0.07
    (/[
    0.07
     unsuitable
    0.07
     largura
    0.07
    Professional
    0.07
    ++;
    ↵
    0.07
    азақ
    0.07
    pora
    0.07
    Activations Density 0.004%

    No Known Activations